• Login
    View Item 
    •   USU-IR Home
    • Faculty of Computer Science and Information Technology
    • Department of Information Technology
    • Master Theses
    • View Item
    •   USU-IR Home
    • Faculty of Computer Science and Information Technology
    • Department of Information Technology
    • Master Theses
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Analisa Kinerja Modifikasi Algoritma Affinity Propagation

    View/Open
    fulltext (36.66Mb)
    Date
    2018
    Author
    Gunawan, Heru
    Advisor(s)
    Suwilo, Saib
    Situmorang, Zakarias
    Metadata
    Show full item record
    Abstract
    Algoritma Affinity Propagation merupakan salah satu algoritma clustering yang berbasis exemplar, pada algoritma ini semua titik data dianggap sebagai calon exemplar. Algoritma Affinity Propagation memiliki kelemahan yaitu sulitnya menentukan nilai Preference yang sesuai agar diperoleh hasil clustering yang baik. Pada algoritma Affinity Propagation standar, nilai Preference dihitung berdasarkan nilai median dari keseluruhan data pada tabel Similarity Matrix. Pada penelitian ini dilakukan modifikasi terhadap algoritma Affinity Propagation dengan melakukan penentuan nilai Preference berdasarkan distribusi data pada masing-masing baris dari tabel Similarity Matrix dengan cara mengurangi nilai median dengan nilai minimum dari masing-masing baris pada tabel Similarity Matrix. Berdasarkan hasil yang diperoleh pada penelitian nilai Silhouette Coefficient yang diperoleh lebih baik bila dibandingkan dengan hasil yang diperoleh dari algoritma Affinity Propagation standar.
     
    Affinity Propagation Algorithm is one of the exemplar-based clustering algorithms, in this algorithm all data points are considered as exemplar candidates. Affinity Propagation algorithm has the disadvantage that it is difficult to determine the appropriate Preference value in order to obtain good clustering results. In the standard Affinity Propagation algorithm, the Preference value is calculated based on the median of the entire data in the Similarity Matrix table. In this research, modification of Affinity Propagation algorithm to determines the Preference value for each row of the Similarity Matrix table, the preference value is preference value is obtained by subtracting the median value with the minimum value of each row in the Similarity Matrix table. Based on the results obtained in this research the Silhouette Coefficient score obtained is better then the results obtained from the standard Affinity Propagation algorithm.

    URI
    http://repositori.usu.ac.id/handle/123456789/8053
    Collections
    • Master Theses [621]

    Repositori Institusi Universitas Sumatera Utara (RI-USU)
    Universitas Sumatera Utara | Perpustakaan | Resource Guide | Katalog Perpustakaan
    DSpace software copyright © 2002-2016  DuraSpace
    Contact Us | Send Feedback
    Theme by 
    Atmire NV
     

     

    Browse

    All of USU-IRCommunities & CollectionsBy Issue DateTitlesAuthorsAdvisorsKeywordsTypesBy Submit DateThis CollectionBy Issue DateTitlesAuthorsAdvisorsKeywordsTypesBy Submit Date

    My Account

    LoginRegister

    Repositori Institusi Universitas Sumatera Utara (RI-USU)
    Universitas Sumatera Utara | Perpustakaan | Resource Guide | Katalog Perpustakaan
    DSpace software copyright © 2002-2016  DuraSpace
    Contact Us | Send Feedback
    Theme by 
    Atmire NV